Insights from customers’ chats with bots and human agents

Purpose The research aims to provide companies knowledge of (1) why customers use the chat feature, (2) who – the agent or the bot – is more similar (in content) to the customer and (3) whether and how this similarity impacts the customer’s engagement during the chat. Design/methodology/approach I conducted three analyses, each of which uses machine learning. Findings Analysis 1 reveals that customers prefer chatting with an agent (vs. the bot) when they seek detailed or sensitive information. Analysis 2 demonstrates that relative to the bot, the agent is more similar (in content) to the customer. Analysis 3 uses guided latent Dirichlet allocation and gradient boosting (XGBoost) to show that matching the customer on the dominant topic boosts customer engagement during the chat. Research limitations/implications The findings help academics know why customers choose an agent versus a bot and whether this choice helps or hurts their engagement. Practical implications The findings help retail managers design better chat features and chatbots, thus improving customer engagement. Originality/value I am aware of no research in marketing or business that has provided evidence on customers’ choice of agent versus bot and the engagement consequences of this choice.